相关论文: Taming Consistency Distillation for Accelerated Hu…

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy…

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…

Recent advancements in diffusion models have positioned them at the forefront of image generation. Despite their superior performance, diffusion models are not without drawbacks; they are characterized by complex architectures and…

Image inpainting methods have shown significant improvements by using deep neural networks recently. However, many of these techniques often create distorted structures or blurry textures inconsistent with surrounding areas. The problem is…

Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality…

We present Acc3D to tackle the challenge of accelerating the diffusion process to generate 3D models from single images. To derive high-quality reconstructions through few-step inferences, we emphasize the critical issue of regularizing the…

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps. LCMs are distilled from pre-trained latent diffusion models…

Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing…

Recent works in dataset distillation seek to minimize training expenses by generating a condensed synthetic dataset that encapsulates the information present in a larger real dataset. These approaches ultimately aim to attain test accuracy…

In this paper, we address the problem of enhancing perceptual quality in video super-resolution (VSR) using Diffusion Models (DMs) while ensuring temporal consistency among frames. We present StableVSR, a VSR method based on DMs that can…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to…

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Video dataset condensation aims to reduce the immense computational cost of video processing. However, it faces a fundamental challenge regarding the inseparable interdependence between spatial appearance and temporal dynamics. Prior work…

Recent advances in video diffusion models have enabled realistic and controllable human image animation with temporal coherence. Although generating reasonable results, existing methods often overlook the need for regional supervision in…

While diffusion models show promising results in image editing given a target prompt, achieving both prompt fidelity and background preservation remains difficult. Recent works have introduced score distillation techniques that leverage the…

Sparse-view Computed Tomography (CT) image reconstruction is a promising approach to reduce radiation exposure, but it inevitably leads to image degradation. Although diffusion model-based approaches are computationally expensive and suffer…

Current diffusion models for human image animation often struggle to maintain identity (ID) consistency, especially when the reference image and driving video differ significantly in body size or position. We introduce StableAnimator++, the…